Search Tools MCP Server

Overview Schema Source Related Servers Discussions Admin

discover_side_effects

Discover all potential side effects of a function call: affected files, network, database, and state changes. Pinpoint risks, guide testing, and prevent unintended consequences.

Instructions

Discover all potential side effects of calling a function or method.

Use this tool when you need to understand:

What else might happen when you call a specific function
All the systems/resources that might be affected by a function call
Potential unintended consequences of code changes
What to test or monitor when modifying a function

Critical for understanding the full impact of code changes, planning testing strategies, or debugging issues that might be caused by unexpected side effects.

Args: repo_path: Repository path (absolute) working_directory: Working directory (absolute path) target_function: Name of the function to analyze for side effects side_effect_patterns: Dictionary mapping effect types to regex patterns. Format: {"category": ["regex1", "regex2", ...]}

    Example:
    {
        "file": [r"open\(", r"\.write\(", r"\.read\(", r"os\.remove", r"pathlib\."],
        "network": [r"requests\.", r"urllib\.", r"\.get\(", r"\.post\("],
        "database": [r"\.execute\(", r"\.query\(", r"\.commit\(", r"session\."],
        "global_state": [r"global ", r"os\.environ", r"setattr\("],
        "logging": [r"log\.", r"logger\.", r"print\("],
        "cache": [r"\.cache", r"redis\.", r"@lru_cache"]
    }
    
    Each regex pattern will be searched for in the function body to identify
    potential side effects. Use Python regex syntax.
trace_depth: How deep to trace function calls for side effects
include_historical_bugs: Whether to analyze git history for side effect bugs

Returns: Comprehensive side effect analysis with risk assessment and mitigation suggestions

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "repo_path": "<repo_path>",
      "working_directory": "<working_directory>",
      "target_function": "<target_function>",
      "side_effect_patterns": "<side_effect_patterns>"
    },
    "name": "discover_side_effects"
  }
}

Input Schema

Name	Required	Description	Default
`repo_path`	Yes
`trace_depth`	No
`target_function`	Yes
`working_directory`	Yes
`side_effect_patterns`	Yes
`include_historical_bugs`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Aug 1, 2026

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the transparency burden. It explains the analysis method (regex pattern search, tracing function calls, git history) and what will be returned (risk assessment, mitigation suggestions). While it does not explicitly state it is read-only, the wording strongly implies non-mutating analysis, and the process details are sufficient for an agent to understand the behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured: purpose, use cases, arguments, and return value. It is somewhat lengthy but each section serves a purpose. The bulleted list of use cases is helpful, though a few lines (e.g., 'Critical for understanding...') are somewhat redundant with the opening sentence.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (6 params, nested objects, no output schema), the description covers the input semantics and high-level return behavior. However, it does not detail the exact structure of the returned analysis or mention error conditions, which could leave an agent uncertain about how to consume the result. Still, it is sufficiently complete for invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the Args section is essential. It explains each parameter, provides a detailed example for the complex 'side_effect_patterns' parameter, and clarifies the behavior of 'trace_depth' and 'include_historical_bugs'. This fully compensates for the lack of schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Discover all potential side effects of calling a function or method.' This clearly distinguishes it from sibling analysis tools by focusing on unintended consequences rather than general code search or dependency tracing.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides a clear bulleted list of when to use the tool ('when you need to understand... what else might happen, affected systems, unintended consequences, what to test'). It does not explicitly state when not to use it or name alternatives, so it stops short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.